Dan Tian

Prof. Dan Tian

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 September 2024 in Sensors
Verified
Journal Article
Open access
PDF file
DTDan Tian
Dan Tian
XYXin Yan
Xin Yan
ZDZhou Don
Zhou Don
WWWangchen Wang
Wangchen Wang
文张文帅 张
文帅 张
With the rapid growth in demand for security surveillance, assisted driving, and remote sensing, object detection networks with robust environmental perception and high detection accuracy have become a research focus. However, single-modality image detection technologies face limitations in environmental adaptability, often affected by factors such as lighting conditions, fog, rain, and obstacles like vegetation, leading to information loss and reduced detection accuracy. We propose an object detection network that integrates features from visible light and infrared images—IV-YOLO—to address these challenges. This network is based on YOLOv8 (You Only Look Once v8) and employs a dual-branch fusion structure that leverages the complementary features of infrared and visible light images for target detection. We designed a Bidirectional Pyramid Feature Fusion structure (Bi-Fusion) to effectively integrate multimodal features, reducing errors from feature redundancy and extracting fine-grained features for small object detection. Additionally, we developed a Shuffle-SPP structure that combines channel and spatial attention to enhance the focus on deep features and extract richer information through upsampling. Regarding model optimization, we designed a loss function tailored for multi-scale object detection, accelerating the convergence speed of the network during training. Compared with the current state-of-the-art Dual-YOLO model, IV-YOLO achieves mAP improvements of 2.8%, 1.1%, and 2.2% on the Drone Vehicle, FLIR, and KAIST datasets, respectively. On the Drone Vehicle and FLIR datasets, IV-YOLO has a parameter count of 4.31 M and achieves a frame rate of 203.2 fps, significantly outperforming YOLOv8n (5.92 M parameters, 188.6 fps on the Drone Vehicle dataset) and YOLO-FIR (7.1 M parameters, 83.3 fps on the FLIR dataset), which had previously achieved the best performance on these datasets. This demonstrates that IV-YOLO achieves higher real-time detection performance while maintaining lower parameter complexity, making it highly promising for applications in autonomous driving, public safety, and beyond.

5 November 2024 in IEEE Access
Verified
Journal Article
Open access
DTDan Tian
Dan Tian
WWWangchen Wang
Wangchen Wang
DZDong Zhou
Dong Zhou
XYXin Yan
Xin Yan
LZLiaoyuan Zeng
Liaoyuan Zeng
With the rapid advancement of drone technology, there has been a significant increase in the demand for detecting “Low, Slow, and Small” (LSS) drones. However, existing deep learning networks often overlook critical details of such small targets during feature extraction, leading to reduced detection accuracy. Furthermore, edge inference devices typically have limited computational power, which hampers real-time processing capabilities. To address these challenges, we propose a lightweight and efficient drone detection network called NFE-YOLO. This network introduces an efficient positive traffic channel attention module known as EOrthoNet and enhances small target detection capabilities by improving the model’s neck structure. Specifically, the neck incorporates partial Convolution and C3Faster modules to reduce model size while the EOrthoNet channel attention module improves feature extraction accuracy.To further enhance the model’s generalization ability, we present a cross-scenario visible-light “Low, Slow, and Small” drone dataset referred to as UESTC Anti-UAV. This dataset comprises a total of 10,099 images that have all been manually annotated with precision to address the issue of insufficient sample diversity in existing datasets.Experimental results demonstrate a significant improvement in detection accuracy across multiple datasets. NFE-YOLO achieves a mAP50 value of 0.987 on the UESTC Anti-UAV dataset representing a 2.3% improvement over YOLOv8n with a model size of only 3.72MB. The proposed method effectively enhances detection accuracy for LSS drones and is crucial for the development of lightweight drone detection models.


28 August 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
XYXin Yan
Xin Yan
DTDan Tian
Dan Tian
DZDong Zhou
Dong Zhou
WWWangchen Wang
Wangchen Wang
文张文帅 张
文帅 张
With the increasing demand for security surveillance, assisted driving, and remote sensing, target detection networks with rich environmental perception capabilities and high detection accuracy have become a research hotspot. However, detection techniques based on single-modality images face limitations in environmental adaptability, as they are easily affected by lighting conditions, as well as obstacles such as smoke, rain, and vegetation, leading to information loss and failing to meet the required accuracy. To address these issues, we propose a target detection network—IV-YOLO, which integrates features from both visible and infrared images. We built a dual-branch fusion network based on YOLOv8 (You Only Look Once v8) that combines infrared and visible images for target detection. On this foundation, we designed a Bidirectional Pyramid Feature Fusion structure (Bi-Fusion) to fully integrate complementary features from different modalities, reducing detection errors caused by feature redundancy and extracting fine-grained features of small targets through dual-modal fusion. Additionally, we developed the Shuffle-SPP structure, which combines channel and spatial attention mechanisms to enhance focus on deep features and further aggregate upsampling, extracting richer features. To improve the model’s expressive power, we designed a loss function tailored for multi-scale target detection boxes, accelerating the network’s convergence during training. Experimental results show that the proposed IV-YOLO network achieves an average precision (mAP) of 74.6% on the UAV remote sensing dataset, 75.4% on the KAIST pedestrian dataset, and 84.8% on the FLIR dataset. While ensuring detection accuracy, our model significantly reduces computational load, making it well-suited to meet real-time requirements. This architecture is expected to find broad application in fields such as autonomous driving, public safety, and others.

1 January 2025 in Computers, Materials & Continua
Verified
Journal Article
Open access
SXShijie Xiang
Shijie Xiang
DZDong Zhou
Dong Zhou
DTDan Tian
Dan Tian
ZWZihao Wang
Zihao Wang
Real-time semantic segmentation tasks place stringent demands on network inference speed, often requiring a reduction in network depth to decrease computational load. However, shallow networks tend to exhibit degradation in feature extraction completeness and inference accuracy. Therefore, balancing high performance with real-time requirements has become a critical issue in the study of real-time semantic segmentation. To address these challenges, this paper proposes a lightweight bilateral dual-residual network. By introducing a novel residual structure combined with feature extraction and fusion modules, the proposed network significantly enhances representational capacity while reducing computational costs. Specifically, an improved compound residual structure is designed to optimize the efficiency of information propagation and feature extraction. Furthermore, the proposed feature extraction and fusion module enables the network to better capture multi-scale information in images, improving the ability to detect both detailed and global semantic features. Experimental results on the publicly available Cityscapes dataset demonstrate that the proposed lightweight dual-branch network achieves outstanding performance while maintaining low computational complexity. In particular, the network achieved a mean Intersection over Union (mIoU) of on the Cityscapes validation set, surpassing many existing semantic segmentation models. Additionally, in terms of inference speed, the network reached frames per second when tested on an NVIDIA GeForce RTX 3090 GPU, significantly improving real-time performance.

5 June 2026 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
HLHongjun Liu
Hongjun Liu
YLYusha Liu
Yusha Liu
GLGuanghui Liu
Guanghui Liu
DTDan Tian
Dan Tian
YSYao Sun
Yao Sun
CLChengxiang Liu
Chengxiang Liu
In affine frequency division multiplexing (AFDM) systems, the severe peak-to-average power ratio (PAPR) signals exist in the time domain due to the coherent superposition of numerous modulated symbols. Eventually, high PAPR signals require sophisticated and expensive power amplifiers with a very large linear range. To this end, a neural network (NN) aided intelligent transceiver optimization framework is proposed for suppressing PAPR based on the spreading AFDM structure. Specifically, the transceiver jointly optimizes the constellation geometry and associated bit labeling, the precoding NN, as well as the NN based detector. Moreover, the precoding NN is learned from a precoding approach which minimizes the variance of the instantaneous power of output signals at the transmitter. The joint optimization framework aims to achieve maximum PAPR reduction under the constraints of unit energy and spectral emission mask. Besides, to mitigate the potential inter-carrier interference during the offline training, a long short term memory based detector is designed within the optimization framework. Simulation results demonstrate that the conceived NN based optimization method achieves a significant enhancement on PAPR reduction compared with conventional approaches, while slightly improving the bit error ratio performance.